Render output to file

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (non-read-only, non-destructive, open-world), the description adds that the file is written by TouchDesigner on the TD machine and uses extension to pick format. This is valuable context for agents understanding that the operation is local to TD and not on the client side. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the main action, and efficient use of an em dash to separate primary purpose from sibling distinction. Every word adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool without output schema, the description covers the main aspects: what it does, format support, location of file writing, and alternative tool. Could mention overwrite behavior or success confirmation but is fairly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are well-described in the schema. The description does not add significant new meaning beyond what is already in the parameter descriptions. The mention of 'pass an absolute path' is already in the file parameter description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool saves a TOP to an image file at native full resolution, and explicitly differentiates from get_preview which only provides a small thumbnail. The verb 'Save' and specific resource 'TOP' with format details make the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It tells when to use (exporting finished frame) and provides a direct comparison to get_preview. The requirement to pass an absolute path and that the file is written on the TD machine is stated. However, it lacks explicit prerequisites such as that the TOP must be cooked or that the file path must be writable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.